U-SEANNet: A Simple, Efficient and Applied U-Shaped Network for Diagnosis of Nasal Diseases on Nasal Endoscopic Images
This work addresses the lack of datasets and inefficient models for nasal disease diagnosis, offering a practical solution for medical applications, though it is incremental as it builds on existing U-shaped architectures.
The paper tackled the problem of diagnosing nasal diseases from endoscopic images by creating the first large-scale dataset (7-NasalEID with 11,352 images) and proposing U-SEANNet, a U-shaped network that achieved 93.58% accuracy with low complexity (0.78M parameters and 0.21 GFLOPs).
Numerous studies have affirmed that deep learning models can facilitate early diagnosis of lesions in endoscopic images. However, the lack of available datasets stymies advancements in research on nasal endoscopy, and existing models fail to strike a good trade-off between model diagnosis performance, model complexity and parameters size, rendering them unsuitable for real-world application. To bridge these gaps, we created the first large-scale nasal endoscopy dataset, named 7-NasalEID, comprising 11,352 images that contain six common nasal diseases and normal samples. Subsequently, we proposed U-SEANNet, an innovative U-shaped architecture, underpinned by depth-wise separable convolution. Moreover, to enhance its capacity for detecting nuanced discrepancies in input images, U-SEANNet employs the Global-Local Channel Feature Fusion module, enabling it to utilize salient channel features from both global and local contexts. To demonstrate U-SEANNet's potential, we benchmarked U-SEANNet against seventeen modern architectures through five-fold cross-validation. The experimental results show that U-SEANNet achieves a commendable accuracy of 93.58%. Notably, U-SEANNet's parameters size and GFLOPs are only 0.78M and 0.21, respectively. Our findings suggest U-SEANNet is the state-of-the-art model for nasal diseases diagnosis in endoscopic images.